https://github.com/rstudio/cheatsheets/raw/master/data-transformation.pdf
local repo version of data-transformation.pdf
29 November, 2020
Data manipulation
Manipulation functions (verbs)
| Task | Function | Package |
|---|---|---|
| Sorting | arrange() |
dplyr |
| Adding columns | mutate() |
dplyr |
| Transformations | mutate() |
dplyr |
| Re-ordering factor levels | factor(,levels=) |
base |
| Re-labelling | factor(,lab=) |
base |
recode() |
dplyr | |
| Re-naming columns | rename(,replace=) |
dplyr |
| Filtering/Subsetting | indexing | base |
| ~ columns | select(,...) |
dplyr |
pull(,...) |
dplyr | |
| ~ rows | filter(,...) |
dplyr |
| Unique combinations | distinct() |
dplyr |
| Reshaping data | pivot_longer(), pivot_wider() |
tidyr |
| Split/combine columns | separate(), unite() |
tidyr |
| Aggregating | group_by() summarise() |
dplyr |
group_by() count() |
dplyr | |
| Merging/joining | *_join() |
dplyr |
Data manipulation grammar
Piping
%>%
data %>%
select(...) %>%
group_by(...) %>%
summarise(...)
Data files
load(file = "../data/manipulationDatasets.RData")
data.1
| Between | Plot | Cond | Time | Temp | LAT | LONG |
|---|---|---|---|---|---|---|
| A1 | P1 | H | 1 | 25.78 | 14.95 | 144.7 |
| A1 | P1 | M | 2 | 24.33 | 16.17 | 142.1 |
| A1 | P1 | L | 3 | 24.96 | 15.53 | 144 |
| A1 | P2 | H | 4 | 25.73 | 14.96 | 145.8 |
| A1 | P2 | M | 1 | 25.05 | 15.61 | 147.7 |
| A1 | P2 | L | 2 | 24.88 | 15.74 | 144.8 |
| A2 | P3 | H | 3 | 20.98 | 19.71 | 145.8 |
| A2 | P3 | M | 4 | 21.39 | 19.27 | 144.9 |
| A2 | P3 | L | 1 | 20.34 | 20.17 | 142.2 |
| A2 | P4 | H | 2 | 20.49 | 19.61 | 144.2 |
| A2 | P4 | M | 3 | 21.52 | 19.11 | 144.2 |
| A2 | P4 | L | 4 | 22.18 | 18.31 | 144.9 |
Data manipulation packages
library(dplyr) library(tidyr) #OR better still library(tidyverse)
Data files
head(data.1)
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145.
#OR data.1 %>% head()
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145.
#OR data.1 %>% head
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145.
Data files
summary(data.1)
## Between Plot Cond Time Temp LAT LONG ## A1:6 P1:3 H:4 Min. :1.00 Min. :20.34 Min. :14.95 Min. :142.1 ## A2:6 P2:3 L:4 1st Qu.:1.75 1st Qu.:21.29 1st Qu.:15.59 1st Qu.:144.1 ## P3:3 M:4 Median :2.50 Median :23.25 Median :17.24 Median :144.7 ## P4:3 Mean :2.50 Mean :23.14 Mean :17.43 Mean :144.6 ## 3rd Qu.:3.25 3rd Qu.:24.99 3rd Qu.:19.35 3rd Qu.:145.1 ## Max. :4.00 Max. :25.78 Max. :20.17 Max. :147.7
Data files
summary(data.1)
## Between Plot Cond Time Temp LAT LONG ## A1:6 P1:3 H:4 Min. :1.00 Min. :20.34 Min. :14.95 Min. :142.1 ## A2:6 P2:3 L:4 1st Qu.:1.75 1st Qu.:21.29 1st Qu.:15.59 1st Qu.:144.1 ## P3:3 M:4 Median :2.50 Median :23.25 Median :17.24 Median :144.7 ## P4:3 Mean :2.50 Mean :23.14 Mean :17.43 Mean :144.6 ## 3rd Qu.:3.25 3rd Qu.:24.99 3rd Qu.:19.35 3rd Qu.:145.1 ## Max. :4.00 Max. :25.78 Max. :20.17 Max. :147.7
data.1 %>% summary()
## Between Plot Cond Time Temp LAT LONG ## A1:6 P1:3 H:4 Min. :1.00 Min. :20.34 Min. :14.95 Min. :142.1 ## A2:6 P2:3 L:4 1st Qu.:1.75 1st Qu.:21.29 1st Qu.:15.59 1st Qu.:144.1 ## P3:3 M:4 Median :2.50 Median :23.25 Median :17.24 Median :144.7 ## P4:3 Mean :2.50 Mean :23.14 Mean :17.43 Mean :144.6 ## 3rd Qu.:3.25 3rd Qu.:24.99 3rd Qu.:19.35 3rd Qu.:145.1 ## Max. :4.00 Max. :25.78 Max. :20.17 Max. :147.7
data.1 %>% summary
## Between Plot Cond Time Temp LAT LONG ## A1:6 P1:3 H:4 Min. :1.00 Min. :20.34 Min. :14.95 Min. :142.1 ## A2:6 P2:3 L:4 1st Qu.:1.75 1st Qu.:21.29 1st Qu.:15.59 1st Qu.:144.1 ## P3:3 M:4 Median :2.50 Median :23.25 Median :17.24 Median :144.7 ## P4:3 Mean :2.50 Mean :23.14 Mean :17.43 Mean :144.6 ## 3rd Qu.:3.25 3rd Qu.:24.99 3rd Qu.:19.35 3rd Qu.:145.1 ## Max. :4.00 Max. :25.78 Max. :20.17 Max. :147.7
Data files
str(data.1)
## tibble [12 × 7] (S3: tbl_df/tbl/data.frame) ## $ Between: Factor w/ 2 levels "A1","A2": 1 1 1 1 1 1 2 2 2 2 ... ## $ Plot : Factor w/ 4 levels "P1","P2","P3",..: 1 1 1 2 2 2 3 3 3 4 ... ## $ Cond : Factor w/ 3 levels "H","L","M": 1 3 2 1 3 2 1 3 2 1 ... ## $ Time : int [1:12] 1 2 3 4 1 2 3 4 1 2 ... ## $ Temp : num [1:12] 25.8 24.3 25 25.7 25.1 ... ## $ LAT : num [1:12] 14.9 16.2 15.5 15 15.6 ... ## $ LONG : num [1:12] 145 142 144 146 148 ...
Dense summary
glimpse(data.1)
## Rows: 12 ## Columns: 7 ## $ Between <fct> A1, A1, A1, A1, A1, A1, A2, A2, A2, A2, A2, A2 ## $ Plot <fct> P1, P1, P1, P2, P2, P2, P3, P3, P3, P4, P4, P4 ## $ Cond <fct> H, M, L, H, M, L, H, M, L, H, M, L ## $ Time <int> 1, 2, 3, 4, 1, 2, 3, 4, 1, 2, 3, 4 ## $ Temp <dbl> 25.77507, 24.32564, 24.96428, 25.73127, 25.05280, 24.88189, 20.97769, 2… ## $ LAT <dbl> 14.94992, 16.16537, 15.53248, 14.95750, 15.61145, 15.73689, 19.70611, 1… ## $ LONG <dbl> 144.6884, 142.0585, 144.0437, 145.8359, 147.7174, 144.7944, 145.7753, 1…
Dataframes and tibbles
Dataframes and tibbles
data.1 %>% as_tibble
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145. ## 7 A2 P3 H 3 21.0 19.7 146. ## 8 A2 P3 M 4 21.4 19.3 145. ## 9 A2 P3 L 1 20.3 20.2 142. ## 10 A2 P4 H 2 20.5 19.6 144. ## 11 A2 P4 M 3 21.5 19.1 144. ## 12 A2 P4 L 4 22.2 18.3 145.
Sorting data
Sorting data (arrange)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Sorting by LAT
data.1 %>% arrange(LAT)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P2 H 4 25.7 15.0 146. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 M 1 25.1 15.6 148. ## 5 A1 P2 L 2 24.9 15.7 145. ## 6 A1 P1 M 2 24.3 16.2 142. ## 7 A2 P4 L 4 22.2 18.3 145. ## 8 A2 P4 M 3 21.5 19.1 144. ## 9 A2 P3 M 4 21.4 19.3 145. ## 10 A2 P4 H 2 20.5 19.6 144. ## 11 A2 P3 H 3 21.0 19.7 146. ## 12 A2 P3 L 1 20.3 20.2 142.
Sorting data (arrange)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Sorting by LAT (descending order)
data.1 %>% arrange(-LAT)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P3 L 1 20.3 20.2 142. ## 2 A2 P3 H 3 21.0 19.7 146. ## 3 A2 P4 H 2 20.5 19.6 144. ## 4 A2 P3 M 4 21.4 19.3 145. ## 5 A2 P4 M 3 21.5 19.1 144. ## 6 A2 P4 L 4 22.2 18.3 145. ## 7 A1 P1 M 2 24.3 16.2 142. ## 8 A1 P2 L 2 24.9 15.7 145. ## 9 A1 P2 M 1 25.1 15.6 148. ## 10 A1 P1 L 3 25.0 15.5 144. ## 11 A1 P2 H 4 25.7 15.0 146. ## 12 A1 P1 H 1 25.8 14.9 145.
Sorting data (arrange)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Sorting by Cond and then TEMP
data.1 %>% arrange(Cond,Temp)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P4 H 2 20.5 19.6 144. ## 2 A2 P3 H 3 21.0 19.7 146. ## 3 A1 P2 H 4 25.7 15.0 146. ## 4 A1 P1 H 1 25.8 14.9 145. ## 5 A2 P3 L 1 20.3 20.2 142. ## 6 A2 P4 L 4 22.2 18.3 145. ## 7 A1 P2 L 2 24.9 15.7 145. ## 8 A1 P1 L 3 25.0 15.5 144. ## 9 A2 P3 M 4 21.4 19.3 145. ## 10 A2 P4 M 3 21.5 19.1 144. ## 11 A1 P1 M 2 24.3 16.2 142. ## 12 A1 P2 M 1 25.1 15.6 148.
Sorting data (arrange)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Sort by the sum of Temp and LAT
data.1 %>% arrange(Temp+LAT)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P4 H 2 20.5 19.6 144. ## 2 A2 P4 L 4 22.2 18.3 145. ## 3 A1 P1 M 2 24.3 16.2 142. ## 4 A1 P1 L 3 25.0 15.5 144. ## 5 A2 P3 L 1 20.3 20.2 142. ## 6 A1 P2 L 2 24.9 15.7 145. ## 7 A2 P4 M 3 21.5 19.1 144. ## 8 A2 P3 M 4 21.4 19.3 145. ## 9 A1 P2 M 1 25.1 15.6 148. ## 10 A2 P3 H 3 21.0 19.7 146. ## 11 A1 P2 H 4 25.7 15.0 146. ## 12 A1 P1 H 1 25.8 14.9 145.
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
- sort by Between and then Cond
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
- sort by Between and then Cond
data.1 %>% arrange(Between,Cond)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P2 H 4 25.7 15.0 146. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 L 2 24.9 15.7 145. ## 5 A1 P1 M 2 24.3 16.2 142. ## 6 A1 P2 M 1 25.1 15.6 148. ## 7 A2 P3 H 3 21.0 19.7 146. ## 8 A2 P4 H 2 20.5 19.6 144. ## 9 A2 P3 L 1 20.3 20.2 142. ## 10 A2 P4 L 4 22.2 18.3 145. ## 11 A2 P3 M 4 21.4 19.3 145. ## 12 A2 P4 M 3 21.5 19.1 144.
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
- sort by Condition and then the ratio of Temp to LAT
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
- sort by Condition and then the ratio of Temp to LAT
data.1 %>% arrange(Cond,Temp/LAT)
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P4 H 2 20.5 19.6 144. ## 2 A2 P3 H 3 21.0 19.7 146. ## 3 A1 P2 H 4 25.7 15.0 146. ## 4 A1 P1 H 1 25.8 14.9 145. ## 5 A2 P3 L 1 20.3 20.2 142. ## 6 A2 P4 L 4 22.2 18.3 145. ## 7 A1 P2 L 2 24.9 15.7 145. ## 8 A1 P1 L 3 25.0 15.5 144. ## 9 A2 P3 M 4 21.4 19.3 145. ## 10 A2 P4 M 3 21.5 19.1 144. ## 11 A1 P1 M 2 24.3 16.2 142. ## 12 A1 P2 M 1 25.1 15.6 148.
Adding columns
Mutate
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% mutate(LL=LAT+LONG)
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG LL ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 160. ## 2 A1 P1 M 2 24.3 16.2 142. 158. ## 3 A1 P1 L 3 25.0 15.5 144. 160. ## 4 A1 P2 H 4 25.7 15.0 146. 161. ## 5 A1 P2 M 1 25.1 15.6 148. 163. ## 6 A1 P2 L 2 24.9 15.7 145. 161. ## 7 A2 P3 H 3 21.0 19.7 146. 165. ## 8 A2 P3 M 4 21.4 19.3 145. 164. ## 9 A2 P3 L 1 20.3 20.2 142. 162. ## 10 A2 P4 H 2 20.5 19.6 144. 164. ## 11 A2 P4 M 3 21.5 19.1 144. 163. ## 12 A2 P4 L 4 22.2 18.3 145. 163.
Mutate
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Transformations
data.1 %>% mutate(logTemp=log(Temp))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG logTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 3.25 ## 2 A1 P1 M 2 24.3 16.2 142. 3.19 ## 3 A1 P1 L 3 25.0 15.5 144. 3.22 ## 4 A1 P2 H 4 25.7 15.0 146. 3.25 ## 5 A1 P2 M 1 25.1 15.6 148. 3.22 ## 6 A1 P2 L 2 24.9 15.7 145. 3.21 ## 7 A2 P3 H 3 21.0 19.7 146. 3.04 ## 8 A2 P3 M 4 21.4 19.3 145. 3.06 ## 9 A2 P3 L 1 20.3 20.2 142. 3.01 ## 10 A2 P4 H 2 20.5 19.6 144. 3.02 ## 11 A2 P4 M 3 21.5 19.1 144. 3.07 ## 12 A2 P4 L 4 22.2 18.3 145. 3.10
Mutate
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Centering
data.1 %>% mutate(MeanTemp=mean(Temp), cTemp=Temp-MeanTemp) ## OR if just want the centered variable.. #data.1 %>% mutate(cTemp=Temp-mean(Temp))
## # A tibble: 12 x 9 ## Between Plot Cond Time Temp LAT LONG MeanTemp cTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 23.1 2.64 ## 2 A1 P1 M 2 24.3 16.2 142. 23.1 1.19 ## 3 A1 P1 L 3 25.0 15.5 144. 23.1 1.83 ## 4 A1 P2 H 4 25.7 15.0 146. 23.1 2.60 ## 5 A1 P2 M 1 25.1 15.6 148. 23.1 1.92 ## 6 A1 P2 L 2 24.9 15.7 145. 23.1 1.75 ## 7 A2 P3 H 3 21.0 19.7 146. 23.1 -2.16 ## 8 A2 P3 M 4 21.4 19.3 145. 23.1 -1.74 ## 9 A2 P3 L 1 20.3 20.2 142. 23.1 -2.79 ## 10 A2 P4 H 2 20.5 19.6 144. 23.1 -2.65 ## 11 A2 P4 M 3 21.5 19.1 144. 23.1 -1.62 ## 12 A2 P4 L 4 22.2 18.3 145. 23.1 -0.957
Mutate
data.1 %>% head(2) %>% as_tibble
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Changing vector types (classes)
data.1 %>% mutate(Time=factor(Time)) %>% as_tibble
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <fct> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145. ## 7 A2 P3 H 3 21.0 19.7 146. ## 8 A2 P3 M 4 21.4 19.3 145. ## 9 A2 P3 L 1 20.3 20.2 142. ## 10 A2 P4 H 2 20.5 19.6 144. ## 11 A2 P4 M 3 21.5 19.1 144. ## 12 A2 P4 L 4 22.2 18.3 145.
Mutate
data.1 %>% head(2) %>% as_tibble
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Changing factor labels
data.1 %>% mutate(Cond=fct_recode(Cond, High='H', Medium='M' )) %>% as_tibble
## # A tibble: 12 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 High 1 25.8 14.9 145. ## 2 A1 P1 Medium 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 High 4 25.7 15.0 146. ## 5 A1 P2 Medium 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145. ## 7 A2 P3 High 3 21.0 19.7 146. ## 8 A2 P3 Medium 4 21.4 19.3 145. ## 9 A2 P3 L 1 20.3 20.2 142. ## 10 A2 P4 High 2 20.5 19.6 144. ## 11 A2 P4 Medium 3 21.5 19.1 144. ## 12 A2 P4 L 4 22.2 18.3 145.
Mutate
data.1 %>% head(2) %>% as_tibble
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Changing factor levels
data.1 %>% pull(Cond)
## [1] H M L H M L H M L H M L ## Levels: H L M
data.1 %>% mutate(Cond=fct_relevel(Cond, c('L', 'M','H'))) %>%
as_tibble() %>% pull(Cond)
## [1] H M L H M L H M L H M L ## Levels: L M H
Mutate
data.1 %>% head(2) %>% as_tibble
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Changing factor levels
data.1 %>% pull(Cond)
## [1] H M L H M L H M L H M L ## Levels: H L M
data.1 %>% mutate(Cond=recode_factor(Cond, 'L'='Low', 'M'='Medium')) %>%
as_tibble() %>% pull(Cond)
## [1] H Medium Low H Medium Low H Medium Low H Medium Low ## Levels: Low Medium H
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% mutate(leadTemp=lead(Temp), lagTemp=lag(Temp))
## # A tibble: 12 x 9 ## Between Plot Cond Time Temp LAT LONG leadTemp lagTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 24.3 NA ## 2 A1 P1 M 2 24.3 16.2 142. 25.0 25.8 ## 3 A1 P1 L 3 25.0 15.5 144. 25.7 24.3 ## 4 A1 P2 H 4 25.7 15.0 146. 25.1 25.0 ## 5 A1 P2 M 1 25.1 15.6 148. 24.9 25.7 ## 6 A1 P2 L 2 24.9 15.7 145. 21.0 25.1 ## 7 A2 P3 H 3 21.0 19.7 146. 21.4 24.9 ## 8 A2 P3 M 4 21.4 19.3 145. 20.3 21.0 ## 9 A2 P3 L 1 20.3 20.2 142. 20.5 21.4 ## 10 A2 P4 H 2 20.5 19.6 144. 21.5 20.3 ## 11 A2 P4 M 3 21.5 19.1 144. 22.2 20.5 ## 12 A2 P4 L 4 22.2 18.3 145. NA 21.5
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Rank orders
data.1 %>% mutate(rankTime=min_rank(Time),
denseRankTime=dense_rank(Time))
## # A tibble: 12 x 9 ## Between Plot Cond Time Temp LAT LONG rankTime denseRankTime ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <int> <int> ## 1 A1 P1 H 1 25.8 14.9 145. 1 1 ## 2 A1 P1 M 2 24.3 16.2 142. 4 2 ## 3 A1 P1 L 3 25.0 15.5 144. 7 3 ## 4 A1 P2 H 4 25.7 15.0 146. 10 4 ## 5 A1 P2 M 1 25.1 15.6 148. 1 1 ## 6 A1 P2 L 2 24.9 15.7 145. 4 2 ## 7 A2 P3 H 3 21.0 19.7 146. 7 3 ## 8 A2 P3 M 4 21.4 19.3 145. 10 4 ## 9 A2 P3 L 1 20.3 20.2 142. 1 1 ## 10 A2 P4 H 2 20.5 19.6 144. 4 2 ## 11 A2 P4 M 3 21.5 19.1 144. 7 3 ## 12 A2 P4 L 4 22.2 18.3 145. 10 4
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Rank orders
data.1 %>% mutate(rowTemp=row_number(Temp), rowTime=row_number(Time),
rankTime=min_rank(Time))
## # A tibble: 12 x 10 ## Between Plot Cond Time Temp LAT LONG rowTemp rowTime rankTime ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <int> <int> <int> ## 1 A1 P1 H 1 25.8 14.9 145. 12 1 1 ## 2 A1 P1 M 2 24.3 16.2 142. 7 4 4 ## 3 A1 P1 L 3 25.0 15.5 144. 9 7 7 ## 4 A1 P2 H 4 25.7 15.0 146. 11 10 10 ## 5 A1 P2 M 1 25.1 15.6 148. 10 2 1 ## 6 A1 P2 L 2 24.9 15.7 145. 8 5 4 ## 7 A2 P3 H 3 21.0 19.7 146. 3 8 7 ## 8 A2 P3 M 4 21.4 19.3 145. 4 11 10 ## 9 A2 P3 L 1 20.3 20.2 142. 1 3 1 ## 10 A2 P4 H 2 20.5 19.6 144. 2 6 4 ## 11 A2 P4 M 3 21.5 19.1 144. 5 9 7 ## 12 A2 P4 L 4 22.2 18.3 145. 6 12 10
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Rank of bins
data.1 %>% mutate(ntile(Temp,4))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG `ntile(Temp, 4)` ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <int> ## 1 A1 P1 H 1 25.8 14.9 145. 4 ## 2 A1 P1 M 2 24.3 16.2 142. 3 ## 3 A1 P1 L 3 25.0 15.5 144. 3 ## 4 A1 P2 H 4 25.7 15.0 146. 4 ## 5 A1 P2 M 1 25.1 15.6 148. 4 ## 6 A1 P2 L 2 24.9 15.7 145. 3 ## 7 A2 P3 H 3 21.0 19.7 146. 1 ## 8 A2 P3 M 4 21.4 19.3 145. 2 ## 9 A2 P3 L 1 20.3 20.2 142. 1 ## 10 A2 P4 H 2 20.5 19.6 144. 1 ## 11 A2 P4 M 3 21.5 19.1 144. 2 ## 12 A2 P4 L 4 22.2 18.3 145. 2
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Logical bins
data.1 %>% mutate(between(Temp,20,25))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG `between(Temp, 20, 25)` ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <lgl> ## 1 A1 P1 H 1 25.8 14.9 145. FALSE ## 2 A1 P1 M 2 24.3 16.2 142. TRUE ## 3 A1 P1 L 3 25.0 15.5 144. TRUE ## 4 A1 P2 H 4 25.7 15.0 146. FALSE ## 5 A1 P2 M 1 25.1 15.6 148. FALSE ## 6 A1 P2 L 2 24.9 15.7 145. TRUE ## 7 A2 P3 H 3 21.0 19.7 146. TRUE ## 8 A2 P3 M 4 21.4 19.3 145. TRUE ## 9 A2 P3 L 1 20.3 20.2 142. TRUE ## 10 A2 P4 H 2 20.5 19.6 144. TRUE ## 11 A2 P4 M 3 21.5 19.1 144. TRUE ## 12 A2 P4 L 4 22.2 18.3 145. TRUE
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Categorical bins
data.1 %>% mutate(fTemp=ifelse(Temp<21, 'Low',
ifelse(between(Temp,21,25), 'Medium', 'High')))
## OR
data.1 %>% mutate(fTemp=case_when(Temp<21 ~ 'Low',
between(Temp, 21, 25) ~ 'Medium',
Temp>25 ~ 'High'))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG fTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <chr> ## 1 A1 P1 H 1 25.8 14.9 145. High ## 2 A1 P1 M 2 24.3 16.2 142. Medium ## 3 A1 P1 L 3 25.0 15.5 144. Medium ## 4 A1 P2 H 4 25.7 15.0 146. High ## 5 A1 P2 M 1 25.1 15.6 148. High ## 6 A1 P2 L 2 24.9 15.7 145. Medium ## 7 A2 P3 H 3 21.0 19.7 146. Low ## 8 A2 P3 M 4 21.4 19.3 145. Medium ## 9 A2 P3 L 1 20.3 20.2 142. Low ## 10 A2 P4 H 2 20.5 19.6 144. Low ## 11 A2 P4 M 3 21.5 19.1 144. Medium ## 12 A2 P4 L 4 22.2 18.3 145. Medium ## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG fTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <chr> ## 1 A1 P1 H 1 25.8 14.9 145. High ## 2 A1 P1 M 2 24.3 16.2 142. Medium ## 3 A1 P1 L 3 25.0 15.5 144. Medium ## 4 A1 P2 H 4 25.7 15.0 146. High ## 5 A1 P2 M 1 25.1 15.6 148. High ## 6 A1 P2 L 2 24.9 15.7 145. Medium ## 7 A2 P3 H 3 21.0 19.7 146. Low ## 8 A2 P3 M 4 21.4 19.3 145. Medium ## 9 A2 P3 L 1 20.3 20.2 142. Low ## 10 A2 P4 H 2 20.5 19.6 144. Low ## 11 A2 P4 M 3 21.5 19.1 144. Medium ## 12 A2 P4 L 4 22.2 18.3 145. Medium
Mutate
Window functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Categorical bins
data.1 %>% mutate(fTemp=cut(Temp, breaks=c(0,21,25,100),
labels=c('Low','Medium','High')))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG fTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <fct> ## 1 A1 P1 H 1 25.8 14.9 145. High ## 2 A1 P1 M 2 24.3 16.2 142. Medium ## 3 A1 P1 L 3 25.0 15.5 144. Medium ## 4 A1 P2 H 4 25.7 15.0 146. High ## 5 A1 P2 M 1 25.1 15.6 148. High ## 6 A1 P2 L 2 24.9 15.7 145. Medium ## 7 A2 P3 H 3 21.0 19.7 146. Low ## 8 A2 P3 M 4 21.4 19.3 145. Medium ## 9 A2 P3 L 1 20.3 20.2 142. Low ## 10 A2 P4 H 2 20.5 19.6 144. Low ## 11 A2 P4 M 3 21.5 19.1 144. Medium ## 12 A2 P4 L 4 22.2 18.3 145. Medium
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Bin Latitude into North, Central and Southern based on Latitude
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Bin Latitude into Northern, Central and Southern based on Latitude
Assuming even spread..
data.1 %>% mutate(Region = cut(LAT, breaks=3,
labels=c('Northern', 'Centeral', 'Southern')))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG Region ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <fct> ## 1 A1 P1 H 1 25.8 14.9 145. Northern ## 2 A1 P1 M 2 24.3 16.2 142. Northern ## 3 A1 P1 L 3 25.0 15.5 144. Northern ## 4 A1 P2 H 4 25.7 15.0 146. Northern ## 5 A1 P2 M 1 25.1 15.6 148. Northern ## 6 A1 P2 L 2 24.9 15.7 145. Northern ## 7 A2 P3 H 3 21.0 19.7 146. Southern ## 8 A2 P3 M 4 21.4 19.3 145. Southern ## 9 A2 P3 L 1 20.3 20.2 142. Southern ## 10 A2 P4 H 2 20.5 19.6 144. Southern ## 11 A2 P4 M 3 21.5 19.1 144. Southern ## 12 A2 P4 L 4 22.2 18.3 145. Centeral
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Bin Latitude into Northern, Central and Southern based on Latitude
data.1 %>% mutate(Region = cut(LAT, breaks=3,
labels=c('Northern', 'Centeral', 'Southern'))) %>%
mutate(Between = fct_inorder(Region))
## # A tibble: 12 x 8 ## Between Plot Cond Time Temp LAT LONG Region ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <fct> ## 1 Northern P1 H 1 25.8 14.9 145. Northern ## 2 Northern P1 M 2 24.3 16.2 142. Northern ## 3 Northern P1 L 3 25.0 15.5 144. Northern ## 4 Northern P2 H 4 25.7 15.0 146. Northern ## 5 Northern P2 M 1 25.1 15.6 148. Northern ## 6 Northern P2 L 2 24.9 15.7 145. Northern ## 7 Southern P3 H 3 21.0 19.7 146. Southern ## 8 Southern P3 M 4 21.4 19.3 145. Southern ## 9 Southern P3 L 1 20.3 20.2 142. Southern ## 10 Southern P4 H 2 20.5 19.6 144. Southern ## 11 Southern P4 M 3 21.5 19.1 144. Southern ## 12 Centeral P4 L 4 22.2 18.3 145. Centeral
Summarising (aggregating) data
Summarise
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% summarise(MeanTemp=mean(Temp), VarTemp=var(Temp), N=n())
## # A tibble: 1 x 3 ## MeanTemp VarTemp N ## <dbl> <dbl> <int> ## 1 23.1 4.66 12
SE <- function(x) sd(x)/sqrt(length(x))
data.1 %>% summarise(MeanTemp=mean(Temp), VarTemp=var(Temp),
SEM=SE(Temp))
## # A tibble: 1 x 3 ## MeanTemp VarTemp SEM ## <dbl> <dbl> <dbl> ## 1 23.1 4.66 0.623
Summarise
Across versions
data.1 %>% summarise(across(c(Temp,LAT), list(Mean=mean, Var=var)))
## # A tibble: 1 x 4 ## Temp_Mean Temp_Var LAT_Mean LAT_Var ## <dbl> <dbl> <dbl> <dbl> ## 1 23.1 4.66 17.4 4.37
data.1 %>% summarise(across(where(is.numeric), list(Mean=mean, Var=var)))
## # A tibble: 1 x 8 ## Time_Mean Time_Var Temp_Mean Temp_Var LAT_Mean LAT_Var LONG_Mean LONG_Var ## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 2.5 1.36 23.1 4.66 17.4 4.37 145. 2.32
data.1 %>% summarize( across(where(is.numeric), mean),
across(where(is.factor), length))
## # A tibble: 1 x 7 ## Time Temp LAT LONG Between Plot Cond ## <dbl> <dbl> <dbl> <dbl> <int> <int> <int> ## 1 2.5 23.1 17.4 145. 12 12 12
Summarise
data.1 %>% count(Cond)
## # A tibble: 3 x 2 ## Cond n ## <fct> <int> ## 1 H 4 ## 2 L 4 ## 3 M 4
data.1 %>% count(Cond,between(Temp,20,30))
## # A tibble: 3 x 3 ## Cond `between(Temp, 20, 30)` n ## <fct> <lgl> <int> ## 1 H TRUE 4 ## 2 L TRUE 4 ## 3 M TRUE 4
Grouping (=aggregating)
Grouping
data.1 %>% head(6)
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145.
data.1 %>% group_by(Between,Plot) %>%
summarise(Mean=mean(Temp))
## # A tibble: 4 x 3 ## # Groups: Between [2] ## Between Plot Mean ## <fct> <fct> <dbl> ## 1 A1 P1 25.0 ## 2 A1 P2 25.2 ## 3 A2 P3 20.9 ## 4 A2 P4 21.4
Grouping
data.1 %>% head(6)
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145.
data.1 %>% group_by(Between,Plot) %>%
summarise(Mean=mean(Temp), Var=var(Temp), N=n(),First=first(Temp))
## # A tibble: 4 x 6 ## # Groups: Between [2] ## Between Plot Mean Var N First ## <fct> <fct> <dbl> <dbl> <int> <dbl> ## 1 A1 P1 25.0 0.528 3 25.8 ## 2 A1 P2 25.2 0.202 3 25.7 ## 3 A2 P3 20.9 0.280 3 21.0 ## 4 A2 P4 21.4 0.724 3 20.5
Grouping
mutate vs summarise
data.1 %>% group_by(Between,Plot) %>%
summarise(Mean=mean(Temp))
## # A tibble: 4 x 3 ## # Groups: Between [2] ## Between Plot Mean ## <fct> <fct> <dbl> ## 1 A1 P1 25.0 ## 2 A1 P2 25.2 ## 3 A2 P3 20.9 ## 4 A2 P4 21.4
data.1 %>% group_by(Between,Plot) %>%
mutate(Mean=mean(Temp))
## # A tibble: 12 x 8 ## # Groups: Between, Plot [4] ## Between Plot Cond Time Temp LAT LONG Mean ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 25.0 ## 2 A1 P1 M 2 24.3 16.2 142. 25.0 ## 3 A1 P1 L 3 25.0 15.5 144. 25.0 ## 4 A1 P2 H 4 25.7 15.0 146. 25.2 ## 5 A1 P2 M 1 25.1 15.6 148. 25.2 ## 6 A1 P2 L 2 24.9 15.7 145. 25.2 ## 7 A2 P3 H 3 21.0 19.7 146. 20.9 ## 8 A2 P3 M 4 21.4 19.3 145. 20.9 ## 9 A2 P3 L 1 20.3 20.2 142. 20.9 ## 10 A2 P4 H 2 20.5 19.6 144. 21.4 ## 11 A2 P4 M 3 21.5 19.1 144. 21.4 ## 12 A2 P4 L 4 22.2 18.3 145. 21.4
Grouping
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% group_by(Between,Plot) %>% mutate(Mean=mean(Temp), cTemp=Temp-Mean)
## # A tibble: 12 x 9 ## # Groups: Between, Plot [4] ## Between Plot Cond Time Temp LAT LONG Mean cTemp ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. 25.0 0.753 ## 2 A1 P1 M 2 24.3 16.2 142. 25.0 -0.696 ## 3 A1 P1 L 3 25.0 15.5 144. 25.0 -0.0574 ## 4 A1 P2 H 4 25.7 15.0 146. 25.2 0.509 ## 5 A1 P2 M 1 25.1 15.6 148. 25.2 -0.169 ## 6 A1 P2 L 2 24.9 15.7 145. 25.2 -0.340 ## 7 A2 P3 H 3 21.0 19.7 146. 20.9 0.0746 ## 8 A2 P3 M 4 21.4 19.3 145. 20.9 0.488 ## 9 A2 P3 L 1 20.3 20.2 142. 20.9 -0.562 ## 10 A2 P4 H 2 20.5 19.6 144. 21.4 -0.905 ## 11 A2 P4 M 3 21.5 19.1 144. 21.4 0.122 ## 12 A2 P4 L 4 22.2 18.3 145. 21.4 0.783
Grouping
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% group_by(Between,Plot) %>% summarise(across(everything(), mean))
## # A tibble: 4 x 7 ## # Groups: Between [2] ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 NA 2 25.0 15.5 144. ## 2 A1 P2 NA 2.33 25.2 15.4 146. ## 3 A2 P3 NA 2.67 20.9 19.7 144. ## 4 A2 P4 NA 3 21.4 19.0 144.
Grouping
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(-Cond,-Time) %>% group_by(Between,Plot) %>%
summarise_all(list(mean))
## # A tibble: 4 x 5 ## # Groups: Between [2] ## Between Plot Temp LAT LONG ## <fct> <fct> <dbl> <dbl> <dbl> ## 1 A1 P1 25.0 15.5 144. ## 2 A1 P2 25.2 15.4 146. ## 3 A2 P3 20.9 19.7 144. ## 4 A2 P4 21.4 19.0 144.
Grouping
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% group_by(Between,Plot) %>%
summarise(across(c(Temp, LAT, LONG), list(Mean=mean, SE=SE)))
## # A tibble: 4 x 8 ## # Groups: Between [2] ## Between Plot Temp_Mean Temp_SE LAT_Mean LAT_SE LONG_Mean LONG_SE ## <fct> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> ## 1 A1 P1 25.0 0.419 15.5 0.351 144. 0.791 ## 2 A1 P2 25.2 0.259 15.4 0.242 146. 0.855 ## 3 A2 P3 20.9 0.305 19.7 0.262 144. 1.06 ## 4 A2 P4 21.4 0.491 19.0 0.379 144. 0.231
Your turn
Calculate for each year, the mean abundance of Pocillopora damicornis
tikus[1:10,c(1:3,76:77)]
## Psammocora contigua Psammocora digitata Pocillopora damicornis time rep ## V1 0 0 79 81 1 ## V2 0 0 51 81 2 ## V3 0 0 42 81 3 ## V4 0 0 15 81 4 ## V5 0 0 9 81 5 ## V6 0 0 72 81 6 ## V7 0 0 0 81 7 ## V8 0 0 16 81 8 ## V9 0 0 0 81 9 ## V10 0 0 16 81 10
NOTE to operate on columns whose names contain special characters (including spaces), you must use `` (backticks).
tikus %>% arrange(`Pocillopora damicornis`)
Your turn
Calculate for each year, the mean abundance of Pocillopora damicornis
tikus %>% group_by(time) %>%
summarise(MeanAbundance=mean(`Pocillopora damicornis`))
## # A tibble: 6 x 2 ## time MeanAbundance ## <fct> <dbl> ## 1 81 30 ## 2 83 0 ## 3 84 0 ## 4 85 0 ## 5 87 1.8 ## 6 88 4
Your turn
Calculate for each year, the number of samples as well as the mean and variance of ozone
nasa = as.data.frame(nasa) head(nasa)
## lat long month year cloudhigh cloudlow cloudmid ozone pressure surftemp temperature ## 1 36.20000 -113.8 1 1995 26.0 7.5 34.5 304 835 272.7 272.1 ## 2 33.70435 -113.8 1 1995 20.0 11.5 32.5 304 940 279.5 282.2 ## 3 31.20870 -113.8 1 1995 16.0 16.5 26.0 298 960 284.7 285.2 ## 4 28.71304 -113.8 1 1995 13.0 20.5 14.5 276 990 289.3 290.7 ## 5 26.21739 -113.8 1 1995 7.5 26.0 10.5 274 1000 292.2 292.7 ## 6 23.72174 -113.8 1 1995 8.0 30.0 9.5 264 1000 294.1 293.6
Your turn
Calculate for each year, the number of samples as well as the mean and variance of ozone
nasa %>% group_by(year) %>%
summarise(N=n(),Mean=mean(ozone), Var=var(ozone))
## # A tibble: 6 x 4 ## year N Mean Var ## <int> <int> <dbl> <dbl> ## 1 1995 6912 264. 258. ## 2 1996 6912 267. 326. ## 3 1997 6912 266. 327. ## 4 1998 6912 267. 507. ## 5 1999 6912 270. 368. ## 6 2000 6912 269. 353.
Subset columns
Selecting columns (select)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(Between,Plot,Cond,Time,Temp)
## # A tibble: 12 x 5 ## Between Plot Cond Time Temp ## <fct> <fct> <fct> <int> <dbl> ## 1 A1 P1 H 1 25.8 ## 2 A1 P1 M 2 24.3 ## 3 A1 P1 L 3 25.0 ## 4 A1 P2 H 4 25.7 ## 5 A1 P2 M 1 25.1 ## 6 A1 P2 L 2 24.9 ## 7 A2 P3 H 3 21.0 ## 8 A2 P3 M 4 21.4 ## 9 A2 P3 L 1 20.3 ## 10 A2 P4 H 2 20.5 ## 11 A2 P4 M 3 21.5 ## 12 A2 P4 L 4 22.2
Selecting columns (select)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(-LAT,-LONG)
## # A tibble: 12 x 5 ## Between Plot Cond Time Temp ## <fct> <fct> <fct> <int> <dbl> ## 1 A1 P1 H 1 25.8 ## 2 A1 P1 M 2 24.3 ## 3 A1 P1 L 3 25.0 ## 4 A1 P2 H 4 25.7 ## 5 A1 P2 M 1 25.1 ## 6 A1 P2 L 2 24.9 ## 7 A2 P3 H 3 21.0 ## 8 A2 P3 M 4 21.4 ## 9 A2 P3 L 1 20.3 ## 10 A2 P4 H 2 20.5 ## 11 A2 P4 M 3 21.5 ## 12 A2 P4 L 4 22.2
Selecting columns (select)
helper functions
contains()ends_with()starts_with()matches()everything()across()- …
must evaluate to TRUE/FALSE
Selecting columns (select)
helper functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(contains('L'))
## # A tibble: 12 x 3 ## Plot LAT LONG ## <fct> <dbl> <dbl> ## 1 P1 14.9 145. ## 2 P1 16.2 142. ## 3 P1 15.5 144. ## 4 P2 15.0 146. ## 5 P2 15.6 148. ## 6 P2 15.7 145. ## 7 P3 19.7 146. ## 8 P3 19.3 145. ## 9 P3 20.2 142. ## 10 P4 19.6 144. ## 11 P4 19.1 144. ## 12 P4 18.3 145.
Selecting columns (select)
helper functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(starts_with('L'))
## # A tibble: 12 x 2 ## LAT LONG ## <dbl> <dbl> ## 1 14.9 145. ## 2 16.2 142. ## 3 15.5 144. ## 4 15.0 146. ## 5 15.6 148. ## 6 15.7 145. ## 7 19.7 146. ## 8 19.3 145. ## 9 20.2 142. ## 10 19.6 144. ## 11 19.1 144. ## 12 18.3 145.
Selecting columns (select)
helper functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(ends_with('t'))
## # A tibble: 12 x 2 ## Plot LAT ## <fct> <dbl> ## 1 P1 14.9 ## 2 P1 16.2 ## 3 P1 15.5 ## 4 P2 15.0 ## 5 P2 15.6 ## 6 P2 15.7 ## 7 P3 19.7 ## 8 P3 19.3 ## 9 P3 20.2 ## 10 P4 19.6 ## 11 P4 19.1 ## 12 P4 18.3
Selecting columns (select)
helper functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(matches('^T[a-z]m.'))
## # A tibble: 12 x 2 ## Time Temp ## <int> <dbl> ## 1 1 25.8 ## 2 2 24.3 ## 3 3 25.0 ## 4 4 25.7 ## 5 1 25.1 ## 6 2 24.9 ## 7 3 21.0 ## 8 4 21.4 ## 9 1 20.3 ## 10 2 20.5 ## 11 3 21.5 ## 12 4 22.2
Regular expressions (regexp)
https://github.com/rstudio/cheatsheets/raw/master/regex.pdf
local repo version of regex.pdf
Selecting columns (select)
helper functions
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% select(Between:Temp)
## # A tibble: 12 x 5 ## Between Plot Cond Time Temp ## <fct> <fct> <fct> <int> <dbl> ## 1 A1 P1 H 1 25.8 ## 2 A1 P1 M 2 24.3 ## 3 A1 P1 L 3 25.0 ## 4 A1 P2 H 4 25.7 ## 5 A1 P2 M 1 25.1 ## 6 A1 P2 L 2 24.9 ## 7 A2 P3 H 3 21.0 ## 8 A2 P3 M 4 21.4 ## 9 A2 P3 L 1 20.3 ## 10 A2 P4 H 2 20.5 ## 11 A2 P4 M 3 21.5 ## 12 A2 P4 L 4 22.2
Your turn
nasa %>% head()
## lat long month year cloudhigh cloudlow cloudmid ozone pressure surftemp temperature ## 1 36.20000 -113.8 1 1995 26.0 7.5 34.5 304 835 272.7 272.1 ## 2 33.70435 -113.8 1 1995 20.0 11.5 32.5 304 940 279.5 282.2 ## 3 31.20870 -113.8 1 1995 16.0 16.5 26.0 298 960 284.7 285.2 ## 4 28.71304 -113.8 1 1995 13.0 20.5 14.5 276 990 289.3 290.7 ## 5 26.21739 -113.8 1 1995 7.5 26.0 10.5 274 1000 292.2 292.7 ## 6 23.72174 -113.8 1 1995 8.0 30.0 9.5 264 1000 294.1 293.6
Select lat, long, and cloud.. columns
Your turn
nasa %>% head()
## lat long month year cloudhigh cloudlow cloudmid ozone pressure surftemp temperature ## 1 36.20000 -113.8 1 1995 26.0 7.5 34.5 304 835 272.7 272.1 ## 2 33.70435 -113.8 1 1995 20.0 11.5 32.5 304 940 279.5 282.2 ## 3 31.20870 -113.8 1 1995 16.0 16.5 26.0 298 960 284.7 285.2 ## 4 28.71304 -113.8 1 1995 13.0 20.5 14.5 276 990 289.3 290.7 ## 5 26.21739 -113.8 1 1995 7.5 26.0 10.5 274 1000 292.2 292.7 ## 6 23.72174 -113.8 1 1995 8.0 30.0 9.5 264 1000 294.1 293.6
nasa %>% select(lat, long, starts_with("cloud")) %>% head
## lat long cloudhigh cloudlow cloudmid ## 1 36.20000 -113.8 26.0 7.5 34.5 ## 2 33.70435 -113.8 20.0 11.5 32.5 ## 3 31.20870 -113.8 16.0 16.5 26.0 ## 4 28.71304 -113.8 13.0 20.5 14.5 ## 5 26.21739 -113.8 7.5 26.0 10.5 ## 6 23.72174 -113.8 8.0 30.0 9.5
Your turn
tikus[1:10,c(1:3,76:77)]
## Psammocora contigua Psammocora digitata Pocillopora damicornis time rep ## V1 0 0 79 81 1 ## V2 0 0 51 81 2 ## V3 0 0 42 81 3 ## V4 0 0 15 81 4 ## V5 0 0 9 81 5 ## V6 0 0 72 81 6 ## V7 0 0 0 81 7 ## V8 0 0 16 81 8 ## V9 0 0 0 81 9 ## V10 0 0 16 81 10
Select rep, time and only Species that DONT contain pora
Your turn
Select rep, time and only Species that DONT contain pora
tikas %>% dplyr::select(-contains('pora'))
## OR if we wanted to alter the order...
tikas %>% dplyr::select(rep, time, everything(),-contains('pora'))
Select awkward names
dplyr::select(tikus, `Pocillopora damicornis`)
## Pocillopora damicornis ## V1 79 ## V2 51 ## V3 42 ## V4 15 ## V5 9 ## V6 72 ## V7 0 ## V8 16 ## V9 0 ## V10 16 ## V11 0 ## V12 0 ## V13 0 ## V14 0 ## V15 0 ## V16 0 ## V17 0 ## V18 0 ## V19 0 ## V20 0 ## V21 0 ## V22 0 ## V23 0 ## V24 0 ## V25 0 ## V26 0 ## V27 0 ## V28 0 ## V29 0 ## V30 0 ## V31 0 ## V32 0 ## V33 0 ## V34 0 ## V35 0 ## V36 0 ## V37 0 ## V38 0 ## V39 0 ## V40 0 ## V41 18 ## V42 0 ## V43 0 ## V44 0 ## V45 0 ## V46 0 ## V47 0 ## V48 0 ## V49 0 ## V50 0 ## V51 0 ## V52 0 ## V53 0 ## V54 0 ## V55 0 ## V56 0 ## V57 10 ## V58 0 ## V59 30 ## V60 0
Selecting a single variable
data.1 %>% pull(Temp)
## [1] 25.77507 24.32564 24.96428 25.73127 25.05280 24.88189 20.97769 21.39090 20.34081 ## [10] 20.48899 21.51637 22.17791
Re-naming columns (vectors)
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% rename(Condition=Cond, Temperature=Temp)
## # A tibble: 12 x 7 ## Between Plot Condition Time Temperature LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 M 1 25.1 15.6 148. ## 6 A1 P2 L 2 24.9 15.7 145. ## 7 A2 P3 H 3 21.0 19.7 146. ## 8 A2 P3 M 4 21.4 19.3 145. ## 9 A2 P3 L 1 20.3 20.2 142. ## 10 A2 P4 H 2 20.5 19.6 144. ## 11 A2 P4 M 3 21.5 19.1 144. ## 12 A2 P4 L 4 22.2 18.3 145.
Filtering
Filtering
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% filter(Cond=='H')
## # A tibble: 4 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P2 H 4 25.7 15.0 146. ## 3 A2 P3 H 3 21.0 19.7 146. ## 4 A2 P4 H 2 20.5 19.6 144.
data.1 %>% filter(Cond %in% c('H','M'))
## # A tibble: 8 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P2 H 4 25.7 15.0 146. ## 4 A1 P2 M 1 25.1 15.6 148. ## 5 A2 P3 H 3 21.0 19.7 146. ## 6 A2 P3 M 4 21.4 19.3 145. ## 7 A2 P4 H 2 20.5 19.6 144. ## 8 A2 P4 M 3 21.5 19.1 144.
Filtering
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% filter(Cond=='H' & Temp<25)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P3 H 3 21.0 19.7 146. ## 2 A2 P4 H 2 20.5 19.6 144.
data.1 %>% filter(Cond=='H' | Temp<25)
## # A tibble: 11 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A1 P2 L 2 24.9 15.7 145. ## 6 A2 P3 H 3 21.0 19.7 146. ## 7 A2 P3 M 4 21.4 19.3 145. ## 8 A2 P3 L 1 20.3 20.2 142. ## 9 A2 P4 H 2 20.5 19.6 144. ## 10 A2 P4 M 3 21.5 19.1 144. ## 11 A2 P4 L 4 22.2 18.3 145.
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Keep only those rows with Temp less than 20 and LAT greater than 20 or LONG less than 145
Your turn
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
Keep only those rows with Temp less than 20 and LAT greater than 20, or LONG less than 145
data.1 %>% filter(Temp<20 & (LAT>20 | LONG <145))
## # A tibble: 0 x 7 ## # … with 7 variables: Between <fct>, Plot <fct>, Cond <fct>, Time <int>, Temp <dbl>, ## # LAT <dbl>, LONG <dbl>
Your turn
glimpse(nasa)
## Rows: 41,472 ## Columns: 11 ## $ lat <dbl> 36.200000, 33.704348, 31.208696, 28.713043, 26.217391, 23.721739, 2… ## $ long <dbl> -113.8000, -113.8000, -113.8000, -113.8000, -113.8000, -113.8000, -… ## $ month <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… ## $ year <int> 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1… ## $ cloudhigh <dbl> 26.0, 20.0, 16.0, 13.0, 7.5, 8.0, 14.5, 19.5, 22.5, 21.0, 19.0, 16.… ## $ cloudlow <dbl> 7.5, 11.5, 16.5, 20.5, 26.0, 30.0, 29.5, 26.5, 27.5, 26.0, 28.5, 28… ## $ cloudmid <dbl> 34.5, 32.5, 26.0, 14.5, 10.5, 9.5, 11.0, 17.5, 18.5, 16.5, 12.5, 13… ## $ ozone <dbl> 304, 304, 298, 276, 274, 264, 258, 252, 250, 250, 248, 248, 250, 24… ## $ pressure <dbl> 835, 940, 960, 990, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,… ## $ surftemp <dbl> 272.7, 279.5, 284.7, 289.3, 292.2, 294.1, 295.0, 298.3, 300.1, 300.… ## $ temperature <dbl> 272.1, 282.2, 285.2, 290.7, 292.7, 293.6, 294.6, 296.9, 297.8, 298.…
Filter to the largest ozone value for the second month of the last year
Your turn
Filter to the largest ozone value for the second month of the last year
nasa %>% filter(year==max(year) & month==2) %>%
arrange(-ozone) %>% head(5)
nasa %>% filter(year==max(year) & month==2) %>%
arrange(-ozone) %>% slice(1:5)
##OR
nasa %>% filter(year==max(year) & month==2 ) %>%
top_n(5, ozone)
Your turn
Filter to all ozone values between 320 and 325 in the first month of the last year
glimpse(nasa)
## Rows: 41,472 ## Columns: 11 ## $ lat <dbl> 36.200000, 33.704348, 31.208696, 28.713043, 26.217391, 23.721739, 2… ## $ long <dbl> -113.8000, -113.8000, -113.8000, -113.8000, -113.8000, -113.8000, -… ## $ month <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1… ## $ year <int> 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1995, 1… ## $ cloudhigh <dbl> 26.0, 20.0, 16.0, 13.0, 7.5, 8.0, 14.5, 19.5, 22.5, 21.0, 19.0, 16.… ## $ cloudlow <dbl> 7.5, 11.5, 16.5, 20.5, 26.0, 30.0, 29.5, 26.5, 27.5, 26.0, 28.5, 28… ## $ cloudmid <dbl> 34.5, 32.5, 26.0, 14.5, 10.5, 9.5, 11.0, 17.5, 18.5, 16.5, 12.5, 13… ## $ ozone <dbl> 304, 304, 298, 276, 274, 264, 258, 252, 250, 250, 248, 248, 250, 24… ## $ pressure <dbl> 835, 940, 960, 990, 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,… ## $ surftemp <dbl> 272.7, 279.5, 284.7, 289.3, 292.2, 294.1, 295.0, 298.3, 300.1, 300.… ## $ temperature <dbl> 272.1, 282.2, 285.2, 290.7, 292.7, 293.6, 294.6, 296.9, 297.8, 298.…
Your turn
Filter to all ozone values between 320 and 325 in the first month of the last year
nasa %>% filter(ozone > 320 & ozone<325, month==first(month),
year==last(year))
##OR
nasa %>% filter(between(ozone,320,325), month==first(month),
year==last(year))
Slicing
Filtering by row number
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% slice(1:4)
## # A tibble: 4 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146.
data.1 %>% slice(c(1:4,7))
## # A tibble: 5 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A1 P2 H 4 25.7 15.0 146. ## 5 A2 P3 H 3 21.0 19.7 146.
Sampling
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% sample_n(10, replace=TRUE)
## # A tibble: 10 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 L 3 25.0 15.5 144. ## 3 A1 P1 L 3 25.0 15.5 144. ## 4 A2 P3 M 4 21.4 19.3 145. ## 5 A1 P2 L 2 24.9 15.7 145. ## 6 A2 P3 H 3 21.0 19.7 146. ## 7 A2 P4 L 4 22.2 18.3 145. ## 8 A1 P2 L 2 24.9 15.7 145. ## 9 A2 P3 M 4 21.4 19.3 145. ## 10 A2 P3 H 3 21.0 19.7 146.
Sampling
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
data.1 %>% sample_frac(0.5, replace=TRUE)
## # A tibble: 6 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A2 P4 M 3 21.5 19.1 144. ## 2 A1 P1 H 1 25.8 14.9 145. ## 3 A1 P2 H 4 25.7 15.0 146. ## 4 A2 P3 M 4 21.4 19.3 145. ## 5 A2 P3 L 1 20.3 20.2 142. ## 6 A2 P3 L 1 20.3 20.2 142.
Effects of filtering
data.1 %>% head(2)
## # A tibble: 2 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142.
#examine the levels of the Cond factor levels(data.1$Cond)
## [1] "H" "L" "M"
Effects of filtering
#subset the dataset to just Cond H data.3 <- data.1 %>% filter(Plot=='P1') #examine subset data data.3
## # A tibble: 3 x 7 ## Between Plot Cond Time Temp LAT LONG ## <fct> <fct> <fct> <int> <dbl> <dbl> <dbl> ## 1 A1 P1 H 1 25.8 14.9 145. ## 2 A1 P1 M 2 24.3 16.2 142. ## 3 A1 P1 L 3 25.0 15.5 144.
#examine the levels of the Cond factor levels(data.3$Cond)
## [1] "H" "L" "M"
levels(data.3$Plot)
## [1] "P1" "P2" "P3" "P4"
levels(data.3$Between)
## [1] "A1" "A2"
Effects of filtering
Correction - all factors
#subset the dataset to just Cond H data.3 <- data.1 %>% filter(Plot=='P1') #drop the unused factor levels from all factors data.3 <- data.3 %>% droplevels() #examine the levels of each factor levels(data.3$Cond)
## [1] "H" "L" "M"
levels(data.3$Plot)
## [1] "P1"
levels(data.3$Between)
## [1] "A1"
Effects of filtering
Correction - single factor
#subset the dataset to just Cond H data.3 <- data.1 %>% filter(Plot=='P1') #drop the unused factor levels from Cond data.3 <- data.3 %>% mutate(Plot=factor(Plot)) #examine the levels of each factor levels(data.3$Cond)
## [1] "H" "L" "M"
levels(data.3$Plot)
## [1] "P1"
levels(data.3$Between)
## [1] "A1" "A2"
Reshaping data
Reshaping data frames
Wide data
| Between | Plot | Time.0 | Time.1 | Time.2 | |
|---|---|---|---|---|---|
| R1 | A1 | P1 | 8 | 14 | 14 |
| R2 | A1 | P2 | 10 | 12 | 11 |
| R3 | A2 | P3 | 7 | 11 | 8 |
| R4 | A2 | P4 | 11 | 9 | 2 |
Wide to long (melt)
data.w %>% pivot_longer(Time.0:Time.2, names_to = 'Time',
values_to='Count')
## OR
data.w %>% pivot_longer(c(-Between, -Plot), names_to = 'Time',
values_to='Count')
## # A tibble: 12 x 4 ## Between Plot Time Count ## <fct> <fct> <chr> <int> ## 1 A1 P1 Time.0 8 ## 2 A1 P1 Time.1 14 ## 3 A1 P1 Time.2 14 ## 4 A1 P2 Time.0 10 ## 5 A1 P2 Time.1 12 ## 6 A1 P2 Time.2 11 ## 7 A2 P3 Time.0 7 ## 8 A2 P3 Time.1 11 ## 9 A2 P3 Time.2 8 ## 10 A2 P4 Time.0 11 ## 11 A2 P4 Time.1 9 ## 12 A2 P4 Time.2 2 ## # A tibble: 12 x 4 ## Between Plot Time Count ## <fct> <fct> <chr> <int> ## 1 A1 P1 Time.0 8 ## 2 A1 P1 Time.1 14 ## 3 A1 P1 Time.2 14 ## 4 A1 P2 Time.0 10 ## 5 A1 P2 Time.1 12 ## 6 A1 P2 Time.2 11 ## 7 A2 P3 Time.0 7 ## 8 A2 P3 Time.1 11 ## 9 A2 P3 Time.2 8 ## 10 A2 P4 Time.0 11 ## 11 A2 P4 Time.1 9 ## 12 A2 P4 Time.2 2
Reshaping data frames
Wide data
| Between | Plot | Time.0 | Time.1 | Time.2 | |
|---|---|---|---|---|---|
| R1 | A1 | P1 | 8 | 14 | 14 |
| R2 | A1 | P2 | 10 | 12 | 11 |
| R3 | A2 | P3 | 7 | 11 | 8 |
| R4 | A2 | P4 | 11 | 9 | 2 |
Wide to long (melt)
## OR
data.w %>% pivot_longer(starts_with('Time'), names_to = 'Time',
values_to='Count',
names_prefix='Time.')
## # A tibble: 12 x 4 ## Between Plot Time Count ## <fct> <fct> <chr> <int> ## 1 A1 P1 0 8 ## 2 A1 P1 1 14 ## 3 A1 P1 2 14 ## 4 A1 P2 0 10 ## 5 A1 P2 1 12 ## 6 A1 P2 2 11 ## 7 A2 P3 0 7 ## 8 A2 P3 1 11 ## 9 A2 P3 2 8 ## 10 A2 P4 0 11 ## 11 A2 P4 1 9 ## 12 A2 P4 2 2
Reshaping data frames
Long data
| Resp1 | Resp2 | Between | Plot | Subplot | Within |
|---|---|---|---|---|---|
| 8 | 17 | A1 | P1 | S1 | B1 |
| 10 | 18 | A1 | P1 | S1 | B2 |
| 7 | 17 | A1 | P1 | S2 | B1 |
| 11 | 21 | A1 | P1 | S2 | B2 |
| 14 | 19 | A2 | P2 | S3 | B1 |
| 12 | 13 | A2 | P2 | S3 | B2 |
| 11 | 24 | A2 | P2 | S4 | B1 |
| 9 | 18 | A2 | P2 | S4 | B2 |
| 14 | 25 | A3 | P3 | S5 | B1 |
| 11 | 18 | A3 | P3 | S5 | B2 |
| 8 | 27 | A3 | P3 | S6 | B1 |
| 2 | 22 | A3 | P3 | S6 | B2 |
| 8 | 17 | A1 | P4 | S7 | B1 |
| 10 | 22 | A1 | P4 | S7 | B2 |
| 7 | 16 | A1 | P4 | S8 | B1 |
| 12 | 13 | A1 | P4 | S8 | B2 |
| 11 | 23 | A2 | P5 | S9 | B1 |
| 12 | 19 | A2 | P5 | S9 | B2 |
| 12 | 23 | A2 | P5 | S10 | B1 |
| 10 | 21 | A2 | P5 | S10 | B2 |
| 3 | 17 | A3 | P6 | S11 | B1 |
| 11 | 16 | A3 | P6 | S11 | B2 |
| 13 | 26 | A3 | P6 | S12 | B1 |
| 7 | 28 | A3 | P6 | S12 | B2 |
Reshaping data frames
data %>% head(2)
## Resp1 Resp2 Between Plot Subplot Within ## 1 8 17 A1 P1 S1 B1 ## 2 10 18 A1 P1 S1 B2
Widen (cast)
Widen Resp1 for repeated measures (Within)
data %>% select(-Resp2) %>% pivot_wider(names_from=Within, values_from=c(Resp1))
## # A tibble: 12 x 5 ## Between Plot Subplot B1 B2 ## <fct> <fct> <fct> <int> <int> ## 1 A1 P1 S1 8 10 ## 2 A1 P1 S2 7 11 ## 3 A2 P2 S3 14 12 ## 4 A2 P2 S4 11 9 ## 5 A3 P3 S5 14 11 ## 6 A3 P3 S6 8 2 ## 7 A1 P4 S7 8 10 ## 8 A1 P4 S8 7 12 ## 9 A2 P5 S9 11 12 ## 10 A2 P5 S10 12 10 ## 11 A3 P6 S11 3 11 ## 12 A3 P6 S12 13 7
Reshaping data frames
Widen Resp1 and Resp2 for repeated measures (Within)
data %>% head(2)
## Resp1 Resp2 Between Plot Subplot Within ## 1 8 17 A1 P1 S1 B1 ## 2 10 18 A1 P1 S1 B2
data %>% pivot_wider(names_from=Within, values_from=c(Resp1, Resp2))
## # A tibble: 12 x 7 ## Between Plot Subplot Resp1_B1 Resp1_B2 Resp2_B1 Resp2_B2 ## <fct> <fct> <fct> <int> <int> <int> <int> ## 1 A1 P1 S1 8 10 17 18 ## 2 A1 P1 S2 7 11 17 21 ## 3 A2 P2 S3 14 12 19 13 ## 4 A2 P2 S4 11 9 24 18 ## 5 A3 P3 S5 14 11 25 18 ## 6 A3 P3 S6 8 2 27 22 ## 7 A1 P4 S7 8 10 17 22 ## 8 A1 P4 S8 7 12 16 13 ## 9 A2 P5 S9 11 12 23 19 ## 10 A2 P5 S10 12 10 23 21 ## 11 A3 P6 S11 3 11 17 16 ## 12 A3 P6 S12 13 7 26 28
Combining data
Merging data frames
Bio data (missing Subplot 3)
| Resp1 | Resp2 | Between | Plot | Subplot | |
|---|---|---|---|---|---|
| 1 | 8 | 18 | A1 | P1 | S1 |
| 2 | 10 | 21 | A1 | P1 | S2 |
| 4 | 11 | 23 | A1 | P2 | S4 |
| 5 | 14 | 22 | A2 | P3 | S5 |
| 6 | 12 | 24 | A2 | P3 | S6 |
| 7 | 11 | 23 | A2 | P4 | S7 |
| 8 | 9 | 20 | A2 | P4 | S8 |
| 9 | 14 | 11 | A3 | P5 | S9 |
| 10 | 11 | 22 | A3 | P5 | S10 |
| 11 | 8 | 24 | A3 | P6 | S11 |
| 12 | 2 | 16 | A3 | P6 | S12 |
Physio-chemical data (missing S7)
| Chem1 | Chem2 | Between | Plot | Subplot | |
|---|---|---|---|---|---|
| 1 | 1.453 | 0.8858 | A1 | P1 | S1 |
| 2 | 3.266 | 0.18 | A1 | P1 | S2 |
| 3 | 1.179 | 5.078 | A1 | P2 | S3 |
| 4 | 13.4 | 1.576 | A1 | P2 | S4 |
| 5 | 3.779 | 1.622 | A2 | P3 | S5 |
| 6 | 1.197 | 4.237 | A2 | P3 | S6 |
| 8 | 5.688 | 2.986 | A2 | P4 | S8 |
| 9 | 4.835 | 4.133 | A3 | P5 | S9 |
| 10 | 2.003 | 3.604 | A3 | P5 | S10 |
| 11 | 12.33 | 1.776 | A3 | P6 | S11 |
| 12 | 4.014 | 0.2255 | A3 | P6 | S12 |
Merging data frames
Merge bio and chem data (only keep full matches - an inner join)
data.bio %>% inner_join(data.chem)
## Resp1 Resp2 Between Plot Subplot Chem1 Chem2 ## 1 8 18 A1 P1 S1 1.452878 0.8858208 ## 2 10 21 A1 P1 S2 3.266253 0.1800177 ## 3 11 23 A1 P2 S4 13.400350 1.5762780 ## 4 14 22 A2 P3 S5 3.779183 1.6222430 ## 5 12 24 A2 P3 S6 1.196657 4.2369184 ## 6 9 20 A2 P4 S8 5.687807 2.9859003 ## 7 14 11 A3 P5 S9 4.834518 4.1328919 ## 8 11 22 A3 P5 S10 2.002931 3.6043314 ## 9 8 24 A3 P6 S11 12.326867 1.7763576 ## 10 2 16 A3 P6 S12 4.014221 0.2255188
- S3 and S7 absent
Merging data frames
Merge bio and chem data (keep all data - outer join)
data.bio %>% full_join(data.chem)
## Resp1 Resp2 Between Plot Subplot Chem1 Chem2 ## 1 8 18 A1 P1 S1 1.452878 0.8858208 ## 2 10 21 A1 P1 S2 3.266253 0.1800177 ## 3 11 23 A1 P2 S4 13.400350 1.5762780 ## 4 14 22 A2 P3 S5 3.779183 1.6222430 ## 5 12 24 A2 P3 S6 1.196657 4.2369184 ## 6 11 23 A2 P4 S7 NA NA ## 7 9 20 A2 P4 S8 5.687807 2.9859003 ## 8 14 11 A3 P5 S9 4.834518 4.1328919 ## 9 11 22 A3 P5 S10 2.002931 3.6043314 ## 10 8 24 A3 P6 S11 12.326867 1.7763576 ## 11 2 16 A3 P6 S12 4.014221 0.2255188 ## 12 NA NA A1 P2 S3 1.178652 5.0780682
- note the order of Subplot
Merging data frames
Merge bio and chem data (only keep full BIO matches - left join)
data.bio %>% left_join(data.chem)
## Resp1 Resp2 Between Plot Subplot Chem1 Chem2 ## 1 8 18 A1 P1 S1 1.452878 0.8858208 ## 2 10 21 A1 P1 S2 3.266253 0.1800177 ## 3 11 23 A1 P2 S4 13.400350 1.5762780 ## 4 14 22 A2 P3 S5 3.779183 1.6222430 ## 5 12 24 A2 P3 S6 1.196657 4.2369184 ## 6 11 23 A2 P4 S7 NA NA ## 7 9 20 A2 P4 S8 5.687807 2.9859003 ## 8 14 11 A3 P5 S9 4.834518 4.1328919 ## 9 11 22 A3 P5 S10 2.002931 3.6043314 ## 10 8 24 A3 P6 S11 12.326867 1.7763576 ## 11 2 16 A3 P6 S12 4.014221 0.2255188
Merging data frames
Merge bio and chem data (only keep full CHEM matches - right join)
data.bio %>% right_join(data.chem)
## Resp1 Resp2 Between Plot Subplot Chem1 Chem2 ## 1 8 18 A1 P1 S1 1.452878 0.8858208 ## 2 10 21 A1 P1 S2 3.266253 0.1800177 ## 3 11 23 A1 P2 S4 13.400350 1.5762780 ## 4 14 22 A2 P3 S5 3.779183 1.6222430 ## 5 12 24 A2 P3 S6 1.196657 4.2369184 ## 6 9 20 A2 P4 S8 5.687807 2.9859003 ## 7 14 11 A3 P5 S9 4.834518 4.1328919 ## 8 11 22 A3 P5 S10 2.002931 3.6043314 ## 9 8 24 A3 P6 S11 12.326867 1.7763576 ## 10 2 16 A3 P6 S12 4.014221 0.2255188 ## 11 NA NA A1 P2 S3 1.178652 5.0780682
VLOOKUP
VLOOKUP
Biological data set (data.bio)
## Resp1 Resp2 Between Plot Subplot ## 1 8 18 A1 P1 S1 ## 2 10 21 A1 P1 S2 ## 4 11 23 A1 P2 S4 ## 5 14 22 A2 P3 S5 ## 6 12 24 A2 P3 S6 ## 7 11 23 A2 P4 S7 ## 8 9 20 A2 P4 S8 ## 9 14 11 A3 P5 S9 ## 10 11 22 A3 P5 S10 ## 11 8 24 A3 P6 S11 ## 12 2 16 A3 P6 S12
Geographical data set (lookup table) (data.geo)
## Plot LAT LONG ## 1 P1 17.9605 145.4326 ## 2 P2 17.5210 146.1983 ## 3 P3 17.0011 146.3839 ## 4 P4 18.2350 146.7934 ## 5 P5 18.9840 146.0345 ## 6 P6 20.1154 146.4672
VLOOKUP
Incorporate (merge) the lat/longs into the bio data
data.bio %>% left_join(data.geo,by=c("Plot"))
## Resp1 Resp2 Between Plot Subplot LAT LONG ## 1 8 18 A1 P1 S1 17.9605 145.4326 ## 2 10 21 A1 P1 S2 17.9605 145.4326 ## 3 11 23 A1 P2 S4 17.5210 146.1983 ## 4 14 22 A2 P3 S5 17.0011 146.3839 ## 5 12 24 A2 P3 S6 17.0011 146.3839 ## 6 11 23 A2 P4 S7 18.2350 146.7934 ## 7 9 20 A2 P4 S8 18.2350 146.7934 ## 8 14 11 A3 P5 S9 18.9840 146.0345 ## 9 11 22 A3 P5 S10 18.9840 146.0345 ## 10 8 24 A3 P6 S11 20.1154 146.4672 ## 11 2 16 A3 P6 S12 20.1154 146.4672
Applied examples
Tikus Island coral data
## Psammocora contigua Psammocora digitata time rep ## V1 0 0 81 1 ## V2 0 0 81 2 ## V3 0 0 81 3 ## V4 0 0 81 4 ## V5 0 0 81 5 ## V6 0 0 81 6 ## V7 0 0 81 7 ## V8 0 0 81 8 ## V9 0 0 81 9 ## V10 0 0 81 10
## Rows: 60 ## Columns: 77 ## $ `Psammocora contigua` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Psammocora digitata` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Pocillopora damicornis` <int> 79, 51, 42, 15, 9, 72, 0, 16, 0, 1… ## $ `Pocillopora verrucosa` <int> 32, 21, 35, 0, 0, 0, 41, 25, 38, 0… ## $ `Stylopora pistillata` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Acropora bruegemanni` <int> 0, 44, 0, 11, 9, 10, 0, 0, 0, 37, … ## $ `Acropora robusta` <int> 0, 35, 40, 0, 0, 0, 0, 0, 0, 0, 0,… ## $ `Acropora grandis` <int> 0, 0, 0, 0, 0, 0, 60, 0, 0, 0, 0, … ## $ `Acropora intermedia` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Acropora formosa` <int> 75, 0, 15, 0, 125, 0, 0, 0, 10, 0,… ## $ `Acropora splendida` <int> 0, 22, 0, 31, 0, 9, 16, 0, 0, 20, … ## $ `Acropera aspera` <int> 17, 18, 9, 8, 23, 0, 17, 13, 16, 1… ## $ `Acropora hyacinthus` <int> 141, 34, 55, 54, 0, 0, 0, 0, 0, 0,… ## $ `Acropora palifera` <int> 32, 0, 44, 0, 17, 0, 0, 0, 0, 0, 0… ## $ `Acropora cytherea` <int> 108, 33, 14, 122, 0, 0, 0, 8, 0, 0… ## $ `Acropora tenuis` <int> 0, 25, 0, 0, 0, 22, 28, 0, 0, 0, 0… ## $ `Acropora pulchra` <int> 0, 0, 15, 52, 62, 33, 0, 0, 24, 0,… ## $ `Acropora nasuta` <int> 43, 21, 19, 0, 0, 0, 10, 0, 0, 0, … ## $ `Acropora humilis` <int> 31, 25, 0, 19, 0, 0, 0, 0, 0, 0, 0… ## $ `Acropora diversa` <int> 22, 19, 20, 13, 23, 14, 0, 12, 12,… ## $ `Acropora digitifera` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Acropora divaricata` <int> 0, 32, 55, 0, 0, 0, 0, 0, 0, 0, 0,… ## $ `Acropora subglabra` <int> 51, 0, 0, 44, 15, 0, 0, 25, 0, 0, … ## $ `Acropora cerealis` <int> 0, 75, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Acropora valida` <int> 0, 0, 0, 30, 0, 0, 0, 0, 0, 0, 0, … ## $ `Acropora acuminata` <int> 20, 0, 71, 0, 15, 0, 25, 25, 0, 0,… ## $ `Acropora elsevi` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Acropora millepora` <int> 17, 14, 0, 20, 0, 0, 0, 0, 0, 0, 0… ## $ `Montipora monasteriata` <int> 60, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Montipora tuberculosa` <int> 0, 15, 15, 0, 0, 0, 0, 0, 0, 0, 0,… ## $ `Montipora hispida` <int> 0, 0, 0, 32, 40, 24, 0, 0, 0, 0, 0… ## $ `Montipora digitata` <int> 0, 0, 0, 0, 0, 77, 84, 53, 71, 351… ## $ `Montipora foliosa` <int> 0, 0, 0, 0, 50, 71, 62, 81, 24, 0,… ## $ `Montipora verrucosa` <int> 0, 0, 30, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Fungia fungites` <int> 0, 0, 18, 17, 0, 0, 0, 0, 0, 0, 0,… ## $ `Fungia paumotensis` <int> 0, 33, 0, 0, 0, 0, 0, 0, 0, 0, 12,… ## $ `Fungia concina` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1… ## $ `Fungia scutaria` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Halomitra limax` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Pavona varians` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 30,… ## $ `Pavona venosa` <int> 0, 24, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Pavona cactus` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Coeloseris mayeri` <int> 20, 0, 15, 0, 9, 19, 0, 0, 25, 0, … ## $ `Galaxea fascicularis` <int> 51, 27, 31, 24, 0, 13, 0, 0, 0, 0,… ## $ `Symphyllia radians` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Lobophyllia corymbosa` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1… ## $ `Lobophyllia hemprichii` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Porites cylindrica` <int> 61, 24, 0, 20, 0, 0, 0, 0, 0, 0, 1… ## $ `Porites lichen` <int> 0, 47, 49, 0, 0, 0, 0, 0, 0, 0, 0,… ## $ `Porites lobata` <int> 36, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Porites lutea` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Porites nigrescens` <int> 0, 0, 0, 21, 0, 9, 25, 0, 45, 26, … ## $ `Porites solida` <int> 0, 0, 10, 0, 17, 0, 31, 41, 0, 0, … ## $ `Porites stephensoni` <int> 0, 0, 0, 0, 0, 0, 0, 30, 0, 0, 0, … ## $ `Goniopora lobata` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Favia pallida` <int> 10, 20, 0, 0, 0, 0, 0, 0, 0, 0, 0,… ## $ `Favia speciosa` <int> 0, 0, 30, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Favia stelligera` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Favia rotumana` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Favites abdita` <int> 33, 41, 23, 27, 91, 63, 72, 48, 71… ## $ `Favites chinensis` <int> 0, 44, 78, 61, 44, 0, 55, 30, 30, … ## $ `Goniastrea rectiformis` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 0… ## $ `Goniastrea pectinata` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Goniastrea sp` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Dulophyllia crispa` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 9… ## $ `Platygyra daedalea` <int> 0, 27, 55, 0, 71, 74, 55, 48, 0, 0… ## $ `Platygyra sinensis` <int> 47, 27, 56, 26, 0, 0, 0, 0, 0, 0, … ## $ `Hydnopora rigida` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Leptastrea purpurea` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Leptastrea pruinosa` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0… ## $ `Cyphastrea serailia` <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 19, … ## $ `Millepora platyphylla` <int> 30, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Millepora dichotoma` <int> 21, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Millepora intrincata` <int> 24, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, … ## $ `Heliopora coerulea` <int> 461, 271, 221, 154, 0, 0, 0, 0, 0,… ## $ time <fct> 81, 81, 81, 81, 81, 81, 81, 81, 81… ## $ rep <fct> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 1, …
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Tikus Island coral data
Explore/Process data
- Convert abundance to cover (abundance is the length in cm of a 10m transect containing the species)
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 1. fix typo (rename) - backticks
tikus %>% rename(`Acropora aspera`=`Acropera aspera`)
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 2. melt data (gather)
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep)
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 3. Calculate Cover (mutate) (Abundance/10)
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10)
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 4. Split species into Genera and Species (separate)
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species'))
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 5. Subset just ‘Acropora’ (filter)
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
filter(Genera=='Acropora')
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 6. Sum over all Species (group_by and summarise)
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
filter(Genera=='Acropora') %>%
group_by(time,rep) %>%
summarise(SumCover=sum(Cover))
Tikus Island coral data
Explore/Process data
- Convert abundance to cover
- Mean cover of total Acropora per year
- NOTE there is a typo ‘Acropera’
Step 7. Summarise per year
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
filter(Genera=='Acropora') %>%
group_by(time,rep) %>%
summarise(SumCover=sum(Cover)) %>%
group_by(time) %>%
summarise(Mean=mean(SumCover),
Var=var(SumCover))
## # A tibble: 6 x 3 ## time Mean Var ## <fct> <dbl> <dbl> ## 1 81 25.6 383. ## 2 83 0 0 ## 3 84 0 0 ## 4 85 2.43 14.2 ## 5 87 8.01 68.5 ## 6 88 8.55 106.
Tikus Island coral data
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
filter(Genera=='Acropora') %>%
group_by(time,rep) %>%
summarise(SumCover=sum(Cover)) %>%
group_by(time) %>%
summarise(Mean=mean(SumCover),
Var=var(SumCover))
## # A tibble: 6 x 3 ## time Mean Var ## <fct> <dbl> <dbl> ## 1 81 25.6 383. ## 2 83 0 0 ## 3 84 0 0 ## 4 85 2.43 14.2 ## 5 87 8.01 68.5 ## 6 88 8.55 106.
Tikus Island coral data
Can you modify so that we get the means and var for each Genera per year?
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
group_by(time,rep,Genera) %>%
summarise(SumCover=sum(Cover)) %>%
group_by(time,Genera) %>%
summarise(Mean=mean(SumCover),
Var=var(SumCover))
## # A tibble: 144 x 4 ## # Groups: time [6] ## time Genera Mean Var ## <fct> <chr> <dbl> <dbl> ## 1 81 Acropora 25.6 383. ## 2 81 Coeloseris 0.88 1.02 ## 3 81 Cyphastrea 0 0 ## 4 81 Dulophyllia 0 0 ## 5 81 Favia 0.6 1.16 ## 6 81 Favites 8.22 14.9 ## 7 81 Fungia 0.68 1.38 ## 8 81 Galaxea 1.46 3.23 ## 9 81 Goniastrea 0 0 ## 10 81 Goniopora 0 0 ## # … with 134 more rows
Tikus Island coral data
What about the means and var for the top 3 Genera per year (sorted from highest to lowest)?
tikus %>% rename(`Acropora aspera`=`Acropera aspera`) %>%
gather(Species, Abundance,-time,-rep) %>%
mutate(Cover=Abundance/10) %>%
separate(Species,c('Genera','Species')) %>%
group_by(time,rep,Genera) %>%
summarise(SumCover=sum(Cover)) %>%
group_by(time,Genera) %>%
summarise(Mean=mean(SumCover),
Var=var(SumCover)) %>%
top_n(3,Mean) %>%
arrange(desc(Mean))
## # A tibble: 18 x 4 ## # Groups: time [6] ## time Genera Mean Var ## <fct> <chr> <dbl> <dbl> ## 1 87 Montipora 27.4 966. ## 2 81 Acropora 25.6 383. ## 3 85 Montipora 20.5 171. ## 4 85 Porites 19.0 51.3 ## 5 88 Montipora 11.8 644. ## 6 81 Montipora 11.4 95.7 ## 7 81 Heliopora 11.1 262. ## 8 84 Montipora 11.0 70.5 ## 9 88 Porites 9.84 41.4 ## 10 88 Acropora 8.55 106. ## 11 87 Acropora 8.01 68.5 ## 12 87 Porites 4.49 35.8 ## 13 84 Porites 2.94 6.65 ## 14 85 Platygyra 2.55 8.74 ## 15 83 Porites 1.74 2.07 ## 16 84 Pavona 1.2 3.33 ## 17 83 Fungia 1.14 3.64 ## 18 83 Montipora 0.93 1.57